LessWrong Team
I have signed no contracts or agreements whose existence I cannot mention.
LessWrong Team
I have signed no contracts or agreements whose existence I cannot mention.
Poll for LW topics you’d like to be tutored in
(please use agree-react to indicate you’d personally like tutoring on a topic, I might reach out if/when I have a prototype)
Added! (Can take a few min to activate though) My advice is for each one of those, ask in it in a new separate/fresh chat because it’ll only a do single search per chat.
I’m not sure where to rate it on easy to set up. It’s not as out of the box as other services.
At this point it seems hardly to add anything to write it explicitly, since I think observers are reaching the same conclusion without help, but I would be utterly horrified to be targeted by Caleb Ditchfield in the way that seems Duncan has been.
It strikes me as an inadequacy of our civilization that someone can perpetuate harms like this and not be stopped. To the extent I have any power to prevent harms like this, e.g. my ~vote on whether Caleb is allowed in communal spaces, I do vote to remove him for the benefit of others.
It is a very sad situation. It seems that Caleb is just very ill, and the worst kind of ill where there’s massive denial and he’ll fight all efforts to persuade him to get help. I hope that writing this comment, not really changing anything, at least pushes in the right direction.
You now have access to the LW LLM Chat prototype!
also think the low-friction integration might make it useful for clarifying math- or programming-heavy posts, though I’m not sure I’ll want this often.
That’s actualy one of my favorite use-cases
You’ve been granted access to the LW LLM Chat prototype!
No need to provide API key (we haven’t even set that up, I was just explaining why we having people manually request access rather than make it immediately available more broadly.
Cheers! Comments here are good, so is LW DM, or Intercom.
Not available on mobile at this time, I’m afraid.
@Neel Nanda @Stephen Fowler @Saul Munn – you’ve been added.
I’m hoping to get a PR deployed today that’ll make a few improvements:
- narrow the width so doesn’t overlap the post on smaller screens than before
- load more posts into the context window by default
- upweight embedding distance relative to karma in the embedding search for relevant context to load in
- various additions to the system response to improve tone and style
Added! That’s been one of my go-to questions for testing variations of the system, I’d suggest just trying it yourself.
I’ll add you now, though I’m in the middle of some changes that should make it better for lit search.
You are added!
Claude 3.5 Sonnet is the chat client, and yes, with RAG using OpenAI text-embedding-3-large
for embeddings.
Oh, you access it with the sparkle button in the bottom right:
Sounds good! I’d recommend pasting in the actual contents together with a description of what you’re after.
@Chris_Leong @Jozdien @Seth Herd @the gears to ascension @ProgramCrafter
You’ve all been granted to the LW integrated LLM Chat prototype. Cheers!
Added!
Added!
Comment here if you’d like access. (Bonus points for describing ways you’d like to use it.)
A couple of months ago, a few of the LW team set out to see how LLMs might be useful in the context of LW. It feels like they should be at some point before the end, maybe that point is now. My own attempts to get Claude to be helpful for writing tasks weren’t particularly succeeding, but LLMs are pretty good at reading a lot of things quickly, and also can be good at explaining technical topics.
So I figured just making it easy to load a lot of relevant LessWrong context into an LLM might unlock several worthwhile use-cases. To that end, Robert and I have integrated a Claude chat window into LW, with the key feature that it will automatically pull in relevant LessWrong posts and comments to what you’re asking about.
I’m currently seeking beta users.
Since using the Claude API isn’t free and we haven’t figured out a payment model, we’re not rolling it out broadly. But we are happy to turn it on for select users who want to try it out.
Comment here if you’d like access. (Bonus points for describing ways you’d like to use it.)
Infra-Bayesianism